Ollama MCP servers

An open-source AI agent framework that enables running multi-agent teams and workflows locally or via cloud providers.

Lets an AI client generate images, video and audio in ComfyUI, author and run workflows, and edit the live node graph in natural language.

Enables AI coding assistants to request second opinions, code reviews, and plan critiques from different LLM providers via their existing CLI subscriptions.

Enables coding assistants to request second opinions and code reviews from different LLM providers using existing subscriptions.

Lets AI clients access your computers' files and run commands in approved folders, and share local models, through one Frely login.

Enables coding assistants to request second opinions from different LLM providers to review code changes or challenge development plans.

Enables AI coding assistants to request second opinions, code reviews, and plan critiques from different LLM providers.

Enables coding assistants to request second opinions and reviews from different LLM providers like Codex, Claude, or local Ollama models.

Enables AI clients to perform agentic RAG with hybrid search, multimodal retrieval, and cited answers from local or cloud-hosted documents.

Lets an AI assistant read and write your self-hosted Nextcloud files, calendars, tasks, contacts, Talk and Deck through 384 MCP tools.

A compaction proxy for OpenAI-compatible local backends that summarizes older conversation turns to prevent context window overflows.

An LLM-maintained personal wiki that ingests sources, cross-references information, and writes structured markdown files on your local disk.

Build AI assistants on your own documents and deploy them across web, WhatsApp, email, and cloud storage platforms.

Lets an AI client read balances, transactions, and monthly summaries from your own bank accounts via open banking.

Runs multi-round debates between multiple AI models and returns a structured synthesis with recommendation, tradeoffs, and disagreements.

Provides observability and governance for local LLMs by scanning prompts for secrets and PII, auditing model usage, and enforcing model policies.

Lets an AI client delegate bounded coding tasks such as reviews, boilerplate and commit messages to local or cloud LLMs.

Build, search, and edit local-first knowledge graphs from documents using GraphRAG and integrated MCP tools.

Lets an AI client chat with any model, run agents and workflows, connect MCP tool servers, and search documents in a self-hosted workspace.

Connects local Ollama LLMs to multiple MCP servers so an AI client can run tools, prompts, and resources from an interactive terminal.

Builds AI agents that interact with real-world APIs using LangChain.js and the Model Context Protocol to perform tasks like ordering food.

Lets an AI client manage local and cloud Ollama models, run chat, generation and embeddings, and search the web.

Gives AI coding agents persistent session memory, local on-device inference, and an auditable token savings report.

An AI meeting recorder for Mac that transcribes calls, provides live assistant suggestions from your documents, and integrates with Claude Desktop.

Enables AI clients to perform hybrid RAG and evidence retrieval using PostgreSQL with pgvector and multi-tenant security.

Lets an AI client inspect Ollama traffic, showing cache hits, prompt cutoffs, timings and tool-call behavior in plain sentences.

Provides shared, source-backed memory for AI agents using a local Postgres database with client isolation and a document engine.

Enables AI clients to perform web scraping, crawling, deep research, and autonomous data extraction with structured Markdown and JSON outputs.

Lets an AI assistant consult other installed AI CLIs like Claude Code, Gemini, and Ollama as a council of models.

Routes ChatGPT, Claude, Gemini, and Perplexity sessions or local models into coding clients as one local MCP endpoint for AI queries.

Provides AI agents with persistent long-term memory, local model routing, and token savings tracking via an MCP server.

Provides a private context layer for AI agents with semantic code search, dependency graphs, and persistent project memory.

Allows AI agents to store and retrieve verbatim Markdown and text notes locally to preserve original context across sessions.

Provides AI assistants with semantic search over WSO2 documentation using RAG and pgvector.

Provides AI assistants with local-first graph memory using SQLite and semantic search to recall, connect, and learn from long-term context.

Serves optimized local LLMs, speech, and image models through OpenAI, Anthropic, and Ollama-compatible APIs.

Lets an AI client build a governed knowledge graph from its own documents and answer questions with cited sources or abstain when evidence is missing.

Lets AI assistants build, edit, and repair Apache JMeter test plans through chat and agent tools.

Enables AI agents to capture microphone audio, perform speech-to-text transcription, and execute voice queries using local models.

Enables AI agents to capture microphone audio, perform speech-to-text transcription, and execute voice queries using local models.

Offloads bulk reading, web research, and test-gated code generation to a local LLM to save frontier-model tokens.

Offloads bulk reading, web research, and test-gated code writing from frontier models to local LLMs to save tokens and context.

Provides a shared, local-first memory layer that allows multiple AI agents to persist and recall preferences, project context, and past decisions.

Turns a large codebase into a searchable hierarchical feature graph an AI client can navigate, analyze, and edit safely.

Lets an AI client control a live Blender session to inspect scenes, create and modify objects, render images, and fetch PolyHaven assets.

Turns a folder of markdown notes into a searchable vector database for AI clients using local or hosted embedding models.

Extracts YouTube transcripts, summarizes videos, monitors channels, and analyzes comments with token-efficient structured reports.

Acts as a local-first semantic librarian that manages large skill collections by providing agents with relevant tool recommendations via embeddings.

Allows an AI client to search, read, and grow a linked Markdown wiki with cited answers from ingested documents.

Connects Claude Desktop to live Squeak or Cuis Smalltalk images to browse classes, evaluate code, and manage methods using an LLM.